Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 403 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0915. Min Range: -2.0915

Max Act: 2.0722. Min Act: -0.0000

Data Index: 1179617 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.9351. Min Act: -0.0000

Data Index: 974919 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 2.0915. Min Range: -2.0915

Max Act: 2.0915. Min Act: -0.0001

Data Index: 308030 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 2.0915. Min Range: -2.0915

Max Act: 2.0107. Min Act: -0.0000

Data Index: 101401 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.9940. Min Act: -0.0000

Data Index: 334223 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.7942. Min Act: -0.0000

Data Index: 1352964 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.8440. Min Act: -0.0001

Data Index: 1530973 (Python Code)

Max Activating Token Index: 612

Text #7

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.8096. Min Act: -0.0000

Data Index: 838208 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.7367. Min Act: -0.0000

Data Index: 1390412 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.7457. Min Act: -0.0000

Data Index: 336824 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.7007. Min Act: -0.0000

Data Index: 816549 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.5568. Min Act: -0.0000

Data Index: 75645 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1313294 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.6479. Min Act: -0.0000

Data Index: 276630 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.4941. Min Act: -0.0000

Data Index: 1172792 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.5511. Min Act: -0.0001

Data Index: 1496729 (Python Code)

Max Activating Token Index: 843

Text #16

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.6182. Min Act: -0.0000

Data Index: 57600 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.4687. Min Act: -0.0001

Data Index: 1619837 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.6113. Min Act: -0.0000

Data Index: 139609 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 2.0915. Min Range: -2.0915

Max Act: 1.5766. Min Act: -0.0000

Data Index: 591509 (C4 (Web Text))

Max Activating Token Index: 586